challenging-america-year-prediction/hf_roberta_base/02_load_dataset.py

import pickle
from datasets import load_dataset
from transformers import AutoTokenizer
from tqdm import tqdm
from sklearn.preprocessing import MinMaxScaler
import numpy as np

dataset = load_dataset('csv', sep='\t', data_files={'train': ['./train_huggingface_format.csv'], 'test': ['./dev-0_huggingface_format.csv']})
test_dataset_A = load_dataset('csv', sep='\t', data_files='test-A_huggingface_format.csv')

tokenizer = AutoTokenizer.from_pretrained('roberta-base')

def tokenize_function(examples):
    t = tokenizer(examples["text"], padding="max_length", truncation=True, max_length=512)
    return t

test_tokenized_datasets_A = test_dataset_A.map(tokenize_function, batched=True)
tokenized_datasets = dataset.map(tokenize_function, batched=True)

train_dataset = tokenized_datasets["train"].shuffle(seed=42)
eval_dataset_full = tokenized_datasets["test"]
eval_dataset_small = tokenized_datasets["test"].select(range(2000))
test_dataset_A = test_tokenized_datasets_A["train"]


scalers = dict()
scalers['year'] = MinMaxScaler().fit(np.array(train_dataset['year']).reshape(-1,1))

def add_scaled(example):
    for factor in ('year',):
        example[factor + '_scaled'] = scalers[factor].transform(np.array(example[factor]).reshape(-1,1)).reshape(1,-1)[0].item()
    return example

train_dataset = train_dataset.map(add_scaled)
eval_dataset_full = eval_dataset_full.map(add_scaled)
eval_dataset_small = eval_dataset_small.map(add_scaled)
#test_dataset_A = test_dataset_A.map(add_scaled)


with open('train_dataset.pickle','wb') as f_p:
    pickle.dump(train_dataset, f_p)

with open('eval_dataset_small.pickle','wb') as f_p:
    pickle.dump(eval_dataset_small, f_p)

with open('eval_dataset_full.pickle','wb') as f_p:
    pickle.dump(eval_dataset_full, f_p)

with open('test_dataset_A.pickle','wb') as f_p:
    pickle.dump(test_dataset_A, f_p)

with open('scalers.pickle','wb') as f_p:
    pickle.dump(scalers, f_p)